Leveraging artificial intelligence to identify high-risk patients for postoperative sore throat: An observational study
Postoperative sore throat (POST) is a prevalent complication after general anesthesia and targeting high-risk patients helps in its prevention. This study developed and validated a machine learning model to predict POST. A total number of 834 patients who underwent general anesthesia with endotrach...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Association of Basic Medical Sciences of Federation of Bosnia and Herzegovina
2023-10-01
|
| Series: | Biomolecules & Biomedicine |
| Subjects: | |
| Online Access: | https://www.bjbms.org/ojs/index.php/bjbms/article/view/9519 |
| _version_ | 1797261351295385600 |
|---|---|
| author | Qiangqiang Zhou Xiaoya Liu Huifang Yun Yahong Zhao Kun Shu Yong Chen Song Chen |
| author_facet | Qiangqiang Zhou Xiaoya Liu Huifang Yun Yahong Zhao Kun Shu Yong Chen Song Chen |
| author_sort | Qiangqiang Zhou |
| collection | DOAJ |
| description |
Postoperative sore throat (POST) is a prevalent complication after general anesthesia and targeting high-risk patients helps in its
prevention. This study developed and validated a machine learning model to predict POST. A total number of 834 patients who
underwent general anesthesia with endotracheal intubation were included in this study. Data from a cohort of 685 patients was used for model development and validation, while a cohort of 149 patients served for external validation. The prediction performance of random forest (RF), neural network (NN), and extreme gradient boosting (XGBoost) models was compared using comprehensive performance metrics. The Local Interpretable Model-Agnostic Explanations (LIME) methods elucidated the best-performing model. POST incidences across training, validation, and testing cohorts were 41.7%, 38.4%, and 36.2%, respectively. Five predictors were age, sex, endotracheal tube cuff pressure, endotracheal tube insertion depth, and the time interval between extubation and the first drinking of water after extubation. After incorporating these variables, the NN model demonstrated superior generalization capabilities in predicting POST when compared to the XGBoost and RF models in external validation, achieving an area under the receiver operating characteristic curve (AUROC) of 0.81 (95% CI 0.74–0.89) and a precision–recall curve (AUPRC) of 0.77 (95% CI 0.66–0.86). The model also showed good calibration and clinical usage values. The NN model outperforms the XGBoost and RF models in predicting POST, with potential applications in the healthcare industry for reducing the incidence of this common postoperative complication.
|
| first_indexed | 2024-04-24T23:39:50Z |
| format | Article |
| id | doaj.art-2be4971b06e141f183000a6784a35a12 |
| institution | Directory Open Access Journal |
| issn | 2831-0896 2831-090X |
| language | English |
| last_indexed | 2024-04-24T23:39:50Z |
| publishDate | 2023-10-01 |
| publisher | Association of Basic Medical Sciences of Federation of Bosnia and Herzegovina |
| record_format | Article |
| series | Biomolecules & Biomedicine |
| spelling | doaj.art-2be4971b06e141f183000a6784a35a122024-03-15T13:22:23ZengAssociation of Basic Medical Sciences of Federation of Bosnia and HerzegovinaBiomolecules & Biomedicine2831-08962831-090X2023-10-0110.17305/bb.2023.9519Leveraging artificial intelligence to identify high-risk patients for postoperative sore throat: An observational studyQiangqiang Zhou0Xiaoya Liu1Huifang Yun2Yahong Zhao3Kun Shu4Yong Chen5Song Chen6Department of Anesthesiology, The Affiliated Changzhou Second People's Hospital of Nanjing Medical University, Changzhou, Jiangsu, ChinaThe Third Affiliated Hospital of Soochow University, Changzhou, Jiangsu, ChinaDepartment of Anesthesiology, The Affiliated Changzhou Second People's Hospital of Nanjing Medical University, Changzhou, Jiangsu, ChinaDepartment of Anesthesiology, The Affiliated Changzhou Second People's Hospital of Nanjing Medical University, Changzhou, Jiangsu, ChinaDepartment of Anesthesiology, The Affiliated Changzhou Second People's Hospital of Nanjing Medical University, Changzhou, Jiangsu, ChinaDepartment of Anesthesiology, The Affiliated Changzhou Second People's Hospital of Nanjing Medical University, Changzhou, Jiangsu, ChinaDepartment of Orthopedics, The Quzhou Affiliated Hospital of Wenzhou Medical University, Quzhou People's Hospital, Quzhou, Zhejiang Province, China Postoperative sore throat (POST) is a prevalent complication after general anesthesia and targeting high-risk patients helps in its prevention. This study developed and validated a machine learning model to predict POST. A total number of 834 patients who underwent general anesthesia with endotracheal intubation were included in this study. Data from a cohort of 685 patients was used for model development and validation, while a cohort of 149 patients served for external validation. The prediction performance of random forest (RF), neural network (NN), and extreme gradient boosting (XGBoost) models was compared using comprehensive performance metrics. The Local Interpretable Model-Agnostic Explanations (LIME) methods elucidated the best-performing model. POST incidences across training, validation, and testing cohorts were 41.7%, 38.4%, and 36.2%, respectively. Five predictors were age, sex, endotracheal tube cuff pressure, endotracheal tube insertion depth, and the time interval between extubation and the first drinking of water after extubation. After incorporating these variables, the NN model demonstrated superior generalization capabilities in predicting POST when compared to the XGBoost and RF models in external validation, achieving an area under the receiver operating characteristic curve (AUROC) of 0.81 (95% CI 0.74–0.89) and a precision–recall curve (AUPRC) of 0.77 (95% CI 0.66–0.86). The model also showed good calibration and clinical usage values. The NN model outperforms the XGBoost and RF models in predicting POST, with potential applications in the healthcare industry for reducing the incidence of this common postoperative complication. https://www.bjbms.org/ojs/index.php/bjbms/article/view/9519Random forest (RF)Neural network (NN)XGBoostPostoperative sore throat (POST) |
| spellingShingle | Qiangqiang Zhou Xiaoya Liu Huifang Yun Yahong Zhao Kun Shu Yong Chen Song Chen Leveraging artificial intelligence to identify high-risk patients for postoperative sore throat: An observational study Biomolecules & Biomedicine Random forest (RF) Neural network (NN) XGBoost Postoperative sore throat (POST) |
| title | Leveraging artificial intelligence to identify high-risk patients for postoperative sore throat: An observational study |
| title_full | Leveraging artificial intelligence to identify high-risk patients for postoperative sore throat: An observational study |
| title_fullStr | Leveraging artificial intelligence to identify high-risk patients for postoperative sore throat: An observational study |
| title_full_unstemmed | Leveraging artificial intelligence to identify high-risk patients for postoperative sore throat: An observational study |
| title_short | Leveraging artificial intelligence to identify high-risk patients for postoperative sore throat: An observational study |
| title_sort | leveraging artificial intelligence to identify high risk patients for postoperative sore throat an observational study |
| topic | Random forest (RF) Neural network (NN) XGBoost Postoperative sore throat (POST) |
| url | https://www.bjbms.org/ojs/index.php/bjbms/article/view/9519 |
| work_keys_str_mv | AT qiangqiangzhou leveragingartificialintelligencetoidentifyhighriskpatientsforpostoperativesorethroatanobservationalstudy AT xiaoyaliu leveragingartificialintelligencetoidentifyhighriskpatientsforpostoperativesorethroatanobservationalstudy AT huifangyun leveragingartificialintelligencetoidentifyhighriskpatientsforpostoperativesorethroatanobservationalstudy AT yahongzhao leveragingartificialintelligencetoidentifyhighriskpatientsforpostoperativesorethroatanobservationalstudy AT kunshu leveragingartificialintelligencetoidentifyhighriskpatientsforpostoperativesorethroatanobservationalstudy AT yongchen leveragingartificialintelligencetoidentifyhighriskpatientsforpostoperativesorethroatanobservationalstudy AT songchen leveragingartificialintelligencetoidentifyhighriskpatientsforpostoperativesorethroatanobservationalstudy |